經(jīng)濟學人雙語精讀TE-2023-05-08期考研英語雜志英文外刊|人工智能：裝病打電話請假（PDF版+Word版+音頻）

5.8每日一篇|英語外刊社|366外刊社

Artificial intelligence：Sickies called
An algorithm candiagnosea cold from changes in someone’s voice
【1】Faking sickness is about to get harder. Sneaking a day off work bynervouslycoughingdown the phone to your boss might no longer cut the mustard—very soon your company might be able to tell whether or not yoursymptomsare real, just from the sound of your voice.
【2】As anyone who haswokenup with arunnynose and a voice like Darth Vader canattest,infectionwith the common coldvirusaltershow a person’s voice sounds. That is because the vocal cords often becomeinflamed, which changes theiracousticproperties. Thetissuetemporarilyswells and, therefore,vibratesat a lower pitch, which tends to make people with a cold develop a deeper voice.
【3】A research team at the Sardar Vallabhbhai National Institute of Technology in Surat, India, tried todecodeexactly how a “cold voice” differs from a healthy voice. Their research makes use of the fact that human speech, like any musicalinstrument, does not produce singlefrequenciesof sounds. Even the best trainedsingerscannot hit pure notes like those that come fromtuningforks. Thedominantnotes in the human voice are insteadaccompaniedby a series of higher-pitchedovertones.
【4】Together these sets of notes fit into mathematicalpatternscalledharmonics, withovertoneshavingfrequenciesthat aremultiplesof the original note. For example, the pitch of the secondharmonicnote is twice thefrequencyof the main note and so on. Theamplitude(loudness) of theseharmonicsin speech tends todiminishas theyproceedup thefrequencyscale. The team of researchers, led by Pankaj Warule, an electronic engineer, reasoned thatinfectionwith a cold mightalterhow thisattenuationhappened.
【5】To find out, the scientists made use of anunusualresource:recordingsof the voices of630people in Germany,111of whom were suffering from a cold. Each was asked to count from one to40and describe what they did at the weekend. They also read aloud Aesop’sfable“The North Wind and the Sun”, which has been a popular text for phonetics research since1949.
【6】By breaking down each person’s speech into itsspectrumofcomponentwavelengths, the researchers couldidentifythedominantfrequencyand theharmonicsin each case. They then used machine-learningalgorithmsto analyse the relationships between theamplitudesof theseharmonicsand foundpatternsthat coulddistinguishthe cold voices from the healthy voices. They reported their work in Biomedical Signal Processing and Control.
【7】It is not just the common cold that can bediagnosedfrom speech in this way. Other scientists are looking at how conditions from Parkinson’s disease anddepressionto head and neck cancers can also affect thepatternsoffrequenciesin a person’s voice. It is part of a wider effort by medics,psychiatristsand computer scientists toremotelydetect biomarkers fordiseasesin data collected on how people talk, write and even walk.
【8】The Indian team’sdiagnosisof cold voice is not yetfoolproof. The results show it can correctlydiagnosea cold up to around70% of the time. Faced with anotherdrearyMonday at the office, would you take the risk?

①短語：1.原文：Sneaking a day off work by nervously coughing down the phone to your boss might no longer cut the mustard.

詞典:cut the mustard 如所期待的那么好；符合要求

例句：Other magazines have tried to copy the formula but have never quitecut the mustard.

其他雜志都想套用這一方法，但都做得不好。

2.原文：The tissue temporarily swells and, therefore, vibrates at a lower pitch, which tends to make people with a cold develop a deeper voice.

詞典:tend to do sth 往往會做某事；傾向于做某事

例句：A problem for manufacturers is that lighter carstend tobe noisy.

制造商們遇到的一個問題是，重量較輕的汽車往往噪音大。

3.原文：Together these sets of notes fit into mathematical patterns called harmonics, with overtones having frequencies that are multiples of the original note.

詞典:fit into 融入；歸屬，適于（種情形或體系）

例句：Most film locations broadlyfit intotwo categories; those on private property and those in a public place.

多數(shù)電影的拍攝場地大致歸為兩類：私人宅院與公共場地。

4.原文：They then used machine-learning algorithms to analyse the relationships between the amplitudes of these harmonics and found patterns that could distinguish the cold voices from the healthy voices.

詞典:distinguish A from B 區(qū)分A和B；A有別于B

例句：There is something about music thatdistinguishesitfromall other art forms.

音樂的某種特質(zhì)使其有別于所有其他藝術(shù)形式。

②長難句

1.原文：Their researchmakes use of the factthathuman speech, like any musical instrument, does not produce single frequencies of sounds.

分析：本句包含一個同位語從句。主句為“Their researchmakes use of the fact”；“thathuman speech... sounds”為同位語從句，對the fact進行解釋說明。

譯文：他們的研究基于這一事實：就像任何樂器一樣，人類語言不會產(chǎn)生單一頻率的聲音。

2.原文：Theythenusedmachine-learning algorithmsto analyse the relationships between the amplitudes of these harmonics andfoundpatternsthatcould distinguish the cold voices from the healthy voices.

分析：本句包含一個限制性定語從句。主句為“Theyusedmachine-learning algorithmsandfoundpatterns”；“to analyse... these harmonics ”為目的狀語；“thatcould ... healthy voices”為限制性定語從句，修飾patterns。

譯文：然后，他們使用機器學習算法來分析這些諧波振幅之間的關(guān)系，找到能夠區(qū)分感冒嗓和健康嗓的模式。

③寫作技巧：

The amplitude (loudness) of these harmonics in speech tends todiminishas theyproceed upthe frequency scale.

這些諧波在語音中的振幅（響度）隨著頻率增加而減小。

The team of researchers, led by Pankaj Warule, an electronic engineer, reasoned that infection with a cold might alter how thisattenuationhappened.

電子工程師潘卡杰·瓦魯爾（Pankaj Warule）領(lǐng)導(dǎo)的研究團隊推斷，感冒可能會改變振幅衰減的發(fā)生方式。

生詞: diminish v.減少，減弱

proceed v.繼續(xù)做

attenuationn.衰減；減弱 動詞形式為attenuate“使減弱；使減少”

本文可積累兩個表示“減少”的詞：diminish和attenuate。

proceed up表示“繼續(xù)向上”，可引申為“增加；上升”。

proceed to do sth表示“繼續(xù)做某事”

proceed against 表示“提起訴訟；起訴”

例句：The government strives to promote renewable energies and energy efficiency in all sectors in order to attenuate the negative effects of climate change

政府努力在所有部門推廣可再生能源和節(jié)能，以期減輕氣候變化帶來的不利影響。

④背景知識：

Harmonics（諧波）：基波（Fundamental）頻率是信號的主要頻率（基頻），在音頻中，它是一個聲音中最低的頻率，基波決定了聲音的音調(diào)。諧波頻率比信號的主要頻率高，是頻率中為基波頻率整數(shù)倍的頻率成分。假設(shè)現(xiàn)在音頻頻率的基波是100Hz，那么諧波就是200Hz、300Hz、400Hz……諧波的作用就是美化聲音賦予色彩。一般對于大多數(shù)人聲或樂器，適當提升基波低端頻率處的均衡量，可以獲得溫暖感與豐滿度，同理，如果聲音太沉悶，也可以衰減基波頻率的均衡量；而提升諧波頻率處的均衡量，能夠增強聲音的現(xiàn)場感與清晰度，同理，如果太刺耳，也可以衰減諧波頻率處的均衡量。

段落大意：

【1】算法能通過人聲診斷感冒，裝病越來越難了。

【2】感冒患者的聲音會發(fā)生變化。

【3】研究團隊正在破解健康嗓和感冒嗓的區(qū)別。

【4】感冒會改變?nèi)寺曋姓穹p的方式。

【5】研究團隊對630位德國人的人聲錄音進行分析。

【6】研究團隊找到了能區(qū)分感冒嗓和健康嗓的方式。

【7】這項技術(shù)還能檢測其他疾病對人聲頻率模式的影響。

【8】這項技術(shù)診斷感冒的正確率高達70%左右。

考研英語雜志經(jīng)濟學人英文外刊|2022年經(jīng)濟學人英文雜志（2022年經(jīng)濟學人周刊英雜志已更新完畢）

366外刊社每日分享英文雜志,考研英語雜志,考研英語外刊雙語精讀,經(jīng)濟學人雜志,英文雜志下載。